© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 19837
    Prev
    Next
    INDEX
    Explanations

    have to / has to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hue
    -0.09
    并éĢļè¿ĩ
    -0.09
    并åIJij
    -0.09
    åĽ°æī°
    -0.08
    æĺİ亮
    -0.08
    è¿ĺæĺ¯ä¼ļ
    -0.08
    sf
    -0.08
     Anat
    -0.08
    åĬ³ç´¯
    -0.08
    æ´ĭæ´ĭ
    -0.08
    POSITIVE LOGITS
    å¿ħé¡»
    0.19
    ä¸Ģå®ļè¦ģ
    0.16
    å¿ħé¡»è¦ģ
    0.16
    åĬ¡å¿ħ
    0.16
    å¿ħéłĪ
    0.15
     phải
    0.15
     must
    0.15
    è¦ģåĿļæĮģ
    0.14
    must
    0.13
    é¡»
    0.12
    Activations Density 0.052%

    No Known Activations